Skip to content
AI Atlas
PaperActive

The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth Probes

arxiv.org/abs/2609.10739

Updated 15 min ago · first seen 11 Sept 2026

paper_01M294FNRKKXKXGEMVYXA0F6ST

Published
11 Sept 2026
T1 · 15 min ago
arXiv
2609.10739
T1 · 15 min ago
Category
cs.LG
T1 · 15 min ago

Abstract

A truth probe fitted where truthful reporting and a task's prescribed action coincide cannot distinguish those targets from its fitting labels alone. We call this failure of semantic identification perfect aliasing. In a controlled binary reporting game, truth and prescribed-action probes fitted on compliant contexts solve the same optimization. On rival contexts their labels are complements, forcing their AUROCs to sum to one; this identity holds across 751 cell-layer pairs to floating-point precision. We separate prescribed output symbols from semantic action using randomized codebooks, then separate truth from prescribed action by fitting on mixed compliant and rival contexts. For a reward-trained Gemma-2-9B policy that answers falsely on all evaluated rival trials, the conventional probe scores $0.006 \pm 0.005$ AUROC across three training seeds, while mixed-fit probes score $1.000$ on the same held-out activations. Mixed fitting uses more training examples and access to labelled rival contexts, so this comparison establishes linear recoverability rather than isolating the benefit of decorrelation. We also show that two compliant-fit probes, both perfect in-distribution, score $0.080$ and $0.986$ on the same rival activations. The findings concern what a probe measures: they do not establish preserved functional belief, causal use of the recovered direction, or a deployable deception detector. Code and aggregate results accompany the paper.

Authors 1

Dylan Jayabahu

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 15 min agohigh

Arxiv announce type
cross

Source:arXiv (Atom API + RSS)T1observed 15 min agohigh

arXiv id
2609.10739

Source:arXiv (Atom API + RSS)T1observed 15 min agohigh

Categories
cs.LG, cs.AI, cs.CL

Source:arXiv (Atom API + RSS)T1observed 15 min agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 15 min agohigh

Primary category
cs.LG

Source:arXiv (Atom API + RSS)T1observed 15 min agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 15 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

15 min ago

Conflicts

None